Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models
Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models
复制标题
DOI：
10.1103/physrevlett.126.032001
复制
发表时间：
2021-01-19
影响因子：
8.6
通讯作者：
Stornati, Paolo
中科院分区：
文献类型：
--
作者：
Nicoli, Kim A.;Anders, Christopher J.;Stornati, Paolo
在这封信中，我们证明了将深度生成机器学习模型应用于格场理论是解决马尔科夫链蒙特卡罗(MCMC)方法有问题的问题的一条很有前途的途径。更具体地说，我们证明了生成模型可以用来估计自由能的绝对值，这与现有的基于MCMC的方法不同，现有的方法仅限于估计自由能差。在详细的数值实验中，我们证明了该方法对二维Phi(4)理论的有效性，并与基于MCMC的方法进行了比较。
In this Letter, we demonstrate that applying deep generative machine learning models for lattice field theory is a promising route for solving problems where Markov chain Monte Carlo (MCMC) methods are problematic. More specifically, we show that generative models can be used to estimate the absolute value of the free energy, which is in contrast to existing MCMC-based methods, which are limited to only estimate free energy differences. We demonstrate the effectiveness of the proposed method for two-dimensional phi(4) theory and compare it to MCMC-based methods in detailed numerical experiments.